© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23552
    Prev
    Next
    INDEX
    Explanations

    years, four, twice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¸ĸ
    -0.08
    ä½łçļĦ人
    -0.07
    ALES
    -0.07
    ड़
    -0.06
    andu
    -0.06
    è¿ĺ没
    -0.06
     Uncomment
    -0.06
    alha
    -0.06
    à¹Ģà¸Ĺà¸ŀ
    -0.06
    hart
    -0.06
    POSITIVE LOGITS
     -*-
    0.07
    <|box_end|>
    0.07
    è®°èĢħäºĨ解åĪ°
    0.07
    æľ¬èµĽåŃ£
    0.07
    ä¼łéĢĴæĽ´å¤ļä¿¡æģ¯
    0.06
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    0.06
    ä¸Ģ度çļĦ
    0.06
     ::=
    0.06
    åıij表æŶéĹ´
    0.06
    æ³ķåŃIJ
    0.06
    Activations Density 0.432%

    No Known Activations